检索结果-内蒙古大学图书馆

2nd International Conference on Advances in Computational Intelligence and Informatics, ICACII 2023

作者： Roy, Asish Kumar Jena, Kalyan Kumar Mohapatra, Debasis Biju Patnaik University of Technology Odisha Rourkela India Nodal Centre Department of Computer Science and Engineering Parala Maharaja Engineering College Berhampur India School of Computer Science and Engineering NIST Institute of Science and Technology Berhampur India Department of Computer Science and Engineering Parala Maharaja Engineering College Berhampur India

ISBN: (纸本)9789819747269

Irrigation system (IS) is considered as a crucial component in the human society. It plays a crucial role for the supply of water to the cultivation fields. So, it is very much essential to predict the water pumping requirement in IS. In this work, an Internet of Things (IoT)-assisted machine intelligence (MI)-based approach is proposed for the prediction of water pumping requirement in IS. This work is focused on the machine learning (ML)-based models such as random forest (RF), CatBoost (CB), K-nearest neighbors (KNN), and stochastic gradient descent (SGD) to perform the prediction. In this work, the water pumping requirement is monitored using IoT-assisted sensors. Here, the water pumping requirement and non-requirement cases are represented using 1 and 0, respectively. This work is carried out using cross-validation (CRV) by taking the number of folds (NFL) as 3, 5, and 10. These models are evaluated using classification accuracy (CA). This work is implemented using Python-based Orange 3.32.0. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Text recognition using improved dual attention based on textual double embedding network with aquila optimization algorithm

引用

International Journal of Information technology (Singapore) 2024年 1-15页

作者： Singhdev, Harsiddhi Gupta, Shruti Srivastava, Vivek Saxena, Apoorva Department of Computer Science and Engineering ABES Engineering College Uttar Pradesh Ghaziabad India Department of Computer Science and Engineering Axis Institute of Technology & amp Management Uttar Pradesh Kanpur India

Text recognition is the process that changes an image of text into a system readable text format. Different approaches were suggested related to text detection but the existing methods accuracy is low and error rate is high. Therefore, a text recognition using Improved Dual-attention based on Textual Double Embedding (IDTDE) with aquila optimization algorithm is proposed in this manuscript for effective text recognition. In this method the input image is taken from several datasets. Usually, the images have some kind of noise in it, and to eliminate that, the Structural interval gradient filtering preprocessing technique is used. Then, the ternary pattern and discrete wavelet technique is use to extract best features. Next, residual-based temporal attention convolutional neural network is utilized for the text classification and character identification are effectively attained by and IDTDE network. The Aquila optimization algorithm is used to optimize the network for best extracted text as output. Experimental outcomes demonstrate that the introduced approach accomplishes the high accuracy rates of 98.14%, 98.89%, and 90.47% on the IIIT5K, ICDAR 2013, and ICDAR 2015 datasets, respectively, surpassing the performance of existing frameworks. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Aquila optimizer Character recognition Gradient filtering Improved self-attention Text recognition

来源：评论

学校读者我要写书评

暂无评论

A Reputation-Based AODV Protocol for Blackhole and Malfunction Nodes Detection and Avoidance

引用

computers, Materials & Continua 2024年第8期80卷 1867-1888页

作者： Qussai M.Yaseen Monther Aldwairi Ahmad Manasrah Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityAjman346United Arab Emirates Department of Computer Information Systems Faculty of Computer and Information TechnologyJordan University of Science and TechnologyIrbid22110Jordan College of Technological Innovation Zayed UniversityAbu Dhabi144534United Arab Emirates Faculty of Information Technology and Computer Science Yarmouk UniversityIrbid21163Jordan Computer Information Systems Higher Colleges of TechnologySharjah341214United Arab Emirates

Enhancing the security of Wireless Sensor Networks(WSNs)improves the usability of their ***,finding solutions to various attacks,such as the blackhole attack,is crucial for the success of WSN *** paper proposes an enhanced version of the AODV(Ad Hoc On-Demand Distance Vector)protocol capable of detecting blackholes and malfunctioning benign nodes in WSNs,thereby avoiding them when delivering *** proposed version employs a network-based reputation system to select the best and most secure path to a *** achieve this goal,the proposed version utilizes the Watchdogs/Pathrater mechanisms in AODV to gather and broadcast reputations to all network nodes to build the network-based reputation *** minimize the network overhead of the proposed approach,the paper uses reputation aggregator nodes only for forwarding reputation ***,to reduce the overhead of updating reputation tables,the paper proposes three mechanisms,which are the prompt broadcast,the regular broadcast,and the light broadcast *** proposed enhanced version has been designed to perform effectively in dynamic environments such as mobile WSNs where nodes,including blackholes,move continuously,which is considered a challenge for other *** the proposed enhanced protocol,a node evaluates the security of different routes to a destination and can select the most secure routing *** paper provides an algorithm that explains the proposed protocol in detail and demonstrates a case study that shows the operations of calculating and updating reputation values when nodes move across different ***,the paper discusses the proposed approach’s overhead analysis to prove the proposed enhancement’s correctness and applicability.

关键词： AODV blackhole malfunction nodes pathrater reputation system wireless sensor networks(WSNs) watchdogs

来源：评论

学校读者我要写书评

暂无评论

Advancing Underwater Communication with NBO-MFO Hybrid Routing in UWSNs 10

Advancing Underwater Communication with NBO-MFO Hybrid Routi...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Kalaiselvan, S.A. Kumar, M.Lenin Amanullah, M. Mani Chigurupati, T.R. Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India Vignan Institute of Technology and Science Department of Electronics and Communications Engineering Telangana India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India Tkr College of Engineering and Technology Department of Computer Science and Engineering Telangana India

ISBN: (纸本)9798350353068

In this research provides a solution for optimizing routing path selection in Underwater Wireless Sensor Networks (UWSNs). The algorithm combines Namib Beetle Optimization (NBO) and Moth-Flame Optimization (MFO), integrating them into the ILEACH methodology for efficient routing path selection. The algorithm operates in an iterative manner, commencing with NBO's feature selection process, evaluating fitness through average classification error and feature selection ratio. Simultaneously, MFO mimics moth behavior, updating positions via a logarithmic spiral function based on flame locations. The mutual learning phase facilitates information exchange between NBO and MFO, enhancing their collective intelligence and refining the routing path selection process. ILEACH's contribution lies in its fitness aggregation and selection methods. It amalgamates various criteria, including energy levels, distances, and node conditions, into a comprehensive fitness metric. Subsequently, ILEACH selectively identifies optimal routing paths aligned with energy-efficient criteria and node statuses, ensuring efficient data transmission and energy conservation within UWSNs. This integrated approach fosters a comprehensive strategy for routing path selection in UWSNs, ensuring sustainability and efficiency in data transmission within challenging underwater environments. © 2024 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Advanced Feature Extraction and Machine Learning Techniques for Classifying Steam Game Feedback

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2025年第1期19卷 107-125页

作者： Al Tawil, Arar Fathi, Hanaa Alzoubi, Sharaf Shaban, Amneh Almazaydeh, Laiali H. Faculty of Information Technology Applied Science Private University Amman Jordan College of Computer Science and Informatics Amman Arab University Amman Jordan College of Engineering AbuDhabi University Abu Dhabi United Arab Emirates

The gaming industry produces vast amounts of user-generated feedback, making it challenging for developers to efficiently analyze and respond to real-time reviews. This study addresses the problem of classifying large-scale unstructured user feedback from Steam reviews. In this paper an approach that integrates traditional machine learning models and deep learning models is proposed. XGBoost is used to manage feature-rich datasets, reducing overfitting. Long-short-term memory (LSTM) and Bi-directional LSTM are used to enhance the accuracy and robustness of classification. Feature extraction techniques, such as sentiment analysis and topic modeling, are employed to enrich the dataset and improve model performance. The experimental results show that the XGBoost model achieved the highest performance with an accuracy of 0.9499 and a ROC-AUC score of 0.6113, demonstrating superior performance in distinguishing between positive and negative feedback. In comparison, deep learning models such as LSTM and Bi-directional LSTM showed lower ROC-AUC scores, indicating less effectiveness in handling the classification task. This approach offers game developers a reliable and scalable solution for classifying user sentiment, leading to better game improvements based on user reviews. © 2025 by the authors of this article.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Autism Detection using InceptionV3 and Security using Blockchain 8

Autism Detection using InceptionV3 and Security using Blockc...

引用

8th International Conference on Electronics, Communication and Aerospace technology, ICECA 2024

作者： Annie Silviya, S.H. Seetha, R. Raja, S. Sriman, B. Rupesh, S. Gopala Krishnan, J. Rajalakshmi Institute of Technology Computer Science Engineering Chennai India Vellore Institute of Technology Computer Science Engineering and Information Systems Vellore India Panimalar Engineering College Computer Science and Engineering Chennai India Institute of Science and Technology Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R&d Chennai India Rajalakshmi Institute of Technology Computer and Communication Engineering Chennai India

ISBN: (纸本)9798350367904

The mental health and well-being of children are critical components of their overall development and future success. In India, only 1 in 6 8 children are diagnosed with autism, since monitoring and addressing the mental health issues among children is a challenge because of various factors. Studies have proven that autism detection can be made possible with the assessment of specific facial features that are used as primary markers for the proposed model. The proposed solution aims to leverage technological advancements, such as deep learning, for detecting autism in children using the aforementioned markers. The model gathers data on the children's facial features and predicts any underlying mental disorder. Since the application collects and analyzes sensitive information from the users, an additional security feature is implemented in the proposed solution using blockchain. Key features of the solution include standardized assessment tools, real-time tracking capabilities, personalized interventions, and seamless communication channels between parents, caregivers, and mental health professionals. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Blockchain based tomato supply chain management 2

Blockchain based tomato supply chain management

引用

2nd International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation, ICAECA 2023

作者： Sudha, V. Aswini, D. Akiladevi, R. Government Polytechnic College Computer Engineering Coimbatore India Kumaraguru College of Technology Computer Science and Engineering Coimbatore India Computer Science and Engineering Rajalakshmi Engineering College Chennai India

ISBN: (纸本)9798350306811

Supply chain in agriculture field is very important as the cultivated goods are sensitive for time and temperature. Most of the time, middlemen act as the price-fixing authorities. The farmer's profit declines as the number of people increases. Additionally, there is no provision for tracking the status of the farming goods throughout transportation. Tomatoes are one of the many products that are time, temperature, and container sensitive. These parameters could be tracked by a centralized system, which would be more advantageous. Blockchain is a distributed database providing tamper proof storage of data. The management of the tomato supply chain based on blockchain is suggested in this research. Customers can use this method to learn how the produce is grown and how the shipping process works. Here, the farmer uses the smart contract to periodically update the blockchain with the crop status. The farmer grows it and sells it once it is ripe for cultivation. As a result, the proposed system enables the customer to be fully informed about the crop and commodities. Additionally, it helps the farmer keep track of their products and maximize their yield's profit. © 2023 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Robust Adversarial Training for Industrial Defect Classification with Long-Tailed Data

Robust Adversarial Training for Industrial Defect Classifica...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Xu, Shuchun Lyu, Jiguang Man, Dapeng Xiong, Hengheng Liu, Tao Yang, Wu College of Computer Science and Technology Harbin Engineering University Harbin China

ISBN: (纸本)9798350368741

Deep neural networks are vulnerable to adversarial examples which fool model predictions by adding imperceptible perturbations to natural examples. Adversarial training is effective in defending against adversarial attacks but faces a challenge with long-tailed data, where the over-compression of tail feature space undermines the reliability of defect classification models. To address this problem, we propose APRCB-AT, a novel adversarial training framework that integrates an adaptive perturbation radius and class-balanced loss. We find a positive correlation between the aggressiveness of adversarial examples and the perturbation radius within a certain range. Based on this, APRCB-AT assigns a larger perturbation radius in a certain range to the tail classes, while incorporating class-balanced loss with regularization to penalize the head classes. The experimental results show that APRCB-AT achieves 70.28% robust accuracy against adversarial attacks, surpassing existing methods, such as LSRG-DRW(67.22%) and REAT(68.06%). © 2025 IEEE.

关键词： Adversarial Attack Adversarial Robustness Deep Learning Defect classification Long-Tailed Distribution

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Deep Learning-Based Model for Tomato Leaf Disease Classification

引用

computers, Materials & Continua 2023年第12期77卷 3969-3992页

作者： Naeem Ullah Javed Ali Khan Sultan Almakdi Mohammed S.Alshehri Mimonah Al Qathrady Eman Abdullah Aldakheel Doaa Sami Khafaga Department of Software Engineering University of Engineering and TechnologyTaxila4400Pakistan Department of Computer Science Faculty of PhysicsEngineeringand Computer ScienceUniversity of HertfordshireHatfieldAL109ABUK Department of Computer Science College of Computer Science and Information SystemNajran UniversityNajran55461Saudi Arabia Departments of Information Systems College of Computer Science and Information SystemsNajran UniversityNajran61441Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia

Tomato leaf diseases significantly impact crop production,necessitating early detection for sustainable *** Learning(DL)has recently shown excellent results in identifying and classifying tomato leaf ***,current DL methods often require substantial computational resources,hindering their application on resource-constrained *** propose the Deep Tomato Detection Network(DTomatoDNet),a lightweight DL-based framework comprising 19 learnable layers for efficient tomato leaf disease classification to overcome *** Convn kernels used in the proposed(DTomatoDNet)framework is 1×1,which reduces the number of parameters and helps in more detailed and descriptive feature extraction for *** proposed DTomatoDNet model is trained from scratch to determine the classification success rate.10,000 tomato leaf images(1000 images per class)from the publicly accessible dataset,covering one healthy category and nine disease categories,are utilized in training the proposed DTomatoDNet *** specifically,we classified tomato leaf images into Target Spot(TS),Early Blight(EB),Late Blight(LB),Bacterial Spot(BS),Leaf Mold(LM),Tomato Yellow Leaf Curl Virus(YLCV),Septoria Leaf Spot(SLS),Spider Mites(SM),Tomato Mosaic Virus(MV),and Tomato Healthy(H).The proposed DTomatoDNet approach obtains a classification accuracy of 99.34%,demonstrating excellent accuracy in differentiating between tomato *** model could be used on mobile platforms because it is lightweight and designed with fewer *** farmers can utilize the proposed DTomatoDNet methodology to detect disease more quickly and easily once it has been integrated into mobile platforms by developing a mobile application.

关键词： CNN deep learning DTomatoDNet tomato leaf disease classification smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Cnn models aided with a metaclassifier for lung Carcinoma classification using histopathological images

引用

Multimedia Tools and Applications 2024年 1-25页

作者： Gautam, Nandita Ghosh, Sohini Sarkar, Ram Department of Computer Science & amp Engineering Jadavpur University Kolkata India Department of Information Technology Netaji Subhash Engineering College Kolkata India

Lung cancer is a dangerous disease with differing treatment plans based on types and location of the cancerous cells. The overall 5-year survival rate for all stages of lung cancer is around 15%. People who smoke are at the highest risk of developing lung cancer. Early detection of lung cancer is crucial for starting early treatment and preventing the disease from spreading. Hence, it can improve people’s chances of survival. Imaging tests, such as a chest computed tomography (CT) scan, can detect lung cancer by providing a more detailed picture. However, the examination of chest CT scans is a challenging task and is prone to subject variability. For this, researchers have developed many computer-aided diagnostic (CAD) systems for the automatic detection of cancer using CT scan images. Misdiagnoses can occur in manual interpretation of images. An automated trained neural network on lung images from healthy and malignant lung cells helps lower the problem. Convolutional neural network (CNN)-based pretrained deep learning models have been used successfully to detect lung cancer. The accuracy of classification is significant to avoid false prediction. This research presents a metalearning based approach for identifying the common types of lung cancer tissues namely, Benign tissue, Squamous Cell Carcinoma, and Adenocarcinoma using LC25000 dataset. All the experiments have been conducted on a publicly available benchmark dataset for lung histopathological images. The features extracted from the penultimate layer (global average pooling) of the transfer learning-based CNN models, namely InceptionResNetV1, EfficientNetB7, and DenseNet121, have been fused together, and the dimensionality reduction has been applied to them before passing to the metaclassifier, which is the Support Vector Machine (SVM) classifier in our case. A quantitative analysis of the proposed algorithm has been conducted through classification accuracy and confusion matrix computation. When compared wit

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：